Text Summarization: News and Beyond

1

Text Summarization:News and Beyond

Kathleen McKeownDepartment of Computer Science

Columbia University

2

Homework questions and information Data sets

Additional summary/document pairs added Not homogeneous

3

Midterm Curve A: 72-93

A- 72-73 A+ 91-93

B: 58-71 B- 58-19 B+ 70-71

C: 47-57 C- 47-50 C+ 56-57

D: 39-46

Solutions are posted on the syllabus

4

Questions (from Sparck Jones) Should we take the reader into account and how?

“Similarly, the notion of a basic summary, i.e., one reflective of the source, makes hidden fact assumptions, for example that the subject knowledge of the output’s readers will be on a par with that of the readers for whom the source was intended. (p. 5)”

Is the state of the art sufficiently mature to allow summarization from intermediate representations and still allow robust processing of domain independent material?

5

Text Summarization at Columbia

Shallow analysis instead of information extraction

Extraction of phrases rather than sentences

Generation from surface representations in place of semantics

6

Problems with Sentence Extraction Extraneous phrases

“The five were apprehended along Interstate 95, heading south in vehicles containing an array of gear including … ... authorities said.”

Dangling noun phrases and pronouns “The five”

MisleadingWhy would the media use this specific word

(fundamentalists), so often with relation to Muslims? *Most of them are radical Baptists, Lutheran and Presbyterian groups.

7

Cut and Paste in Professional Summarization

Humans also reuse the input text to produce summaries

But they “cut and paste” the input rather than simply extract our automatic corpus analysis

300 summaries, 1,642 sentences 81% sentences were constructed by cutting

and pasting linguistic studies

8

Major Cut and Paste Operations (1) Sentence reduction

~~~~~~~~~~~~

9


~~~~~~~~~~~~

10


(2) Sentence Combination

~~~~~~~~~~~~

~~~~~~~~~~~~~~ ~~~~~~

11

Major Cut and Paste Operations (3) Syntactic Transformation

(4) Lexical paraphrasing

~~~~~

~~~~~~~~~~~

~~~~~

~~~

12

Summarization at Columbia

News Email Meetings Journal articles Open-ended question-answering

What is a Loya Jurga? Who is Mohammed Naeem Noor Khan? What do people think of welfare reform?

13

Summarization at Columbia

News Single Document Multi-document

Email Meetings Journal articles Open-ended question-answering

What is a Loya Jurga? Who is Al Sadr? What do people think of welfare reform?

14

Cut and Paste Based Single Document Summarization -- System Architecture

Extraction

Sentence reduction

Generation

Sentence combination

Input: single document

Extracted sentences

Output: summary

Corpus

Decomposition

Lexicon

Parser

Co-reference

15

(1) Decomposition of Human-written Summary Sentences

Input: a human-written summary sentence the original document

Decomposition analyzes how the summary sentence was constructed

The need for decomposition provide training and testing data for

studying cut and paste operations

16

Sample Decomposition OutputSummary sentence: Arthur B. Sackler, vice

president for law and public policy of Time Warner Cable Inc. and a member of the direct marketing association told the Communications Subcommittee of the Senate Commerce Committee that legislation to protect children’s privacy on-line could destroy the spondtaneous nature that makes the Internet unique.

Document sentences:S1: A proposed new law that would require web publishers to obtain parental consent before collecting personal information from children could destroy the spontaneous nature that makes the internet unique, a member of the Direct Marketing Association told a Senate panel Thursday.S2: Arthur B. Sackler, vice president for law and public policy of Time Warner Cable Inc., said the association supported efforts to protect children on-line, but he…S3: “For example, a child’s e-mail address is necessary …,” Sackler said in testimony to the Communications subcommittee of the SenateCommerce Committee.S5: The subcommittee is considering the Children’s Online Privacy Act, which was drafted…

17

Decomposition of human-written summaries

Summary sentence: Arthur B. Sackler, vice



A Sample Decomposition Output

18






19






20

The Algorithm for Decomposition A Hidden Markov Model based solution Evaluations:

Human judgements 50 summaries, 305 sentences 93.8% of the sentences were decomposed

correctly Summary sentence alignment Tested in a legal domain

Details in (Jing&McKeown-SIGIR99)

21

(2) Sentence Reduction

An example:Original Sentence: When it arrives sometime next year

in new TV sets, the V-chip will give parents a new and potentially revolutionary device to block out programs they don’t want their children to see.

Reduction Program: The V-chip will give parents a new and potentially revolutionary device to block out programs they don’t want their children to see.

Professional: The V-chip will give parents a device to block out programs they don’t want their children to see.

22

The Algorithm for Sentence Reduction Preprocess: syntactic parsing Step 1: Use linguistic knowledge to decide

what phrases MUST NOT be removed Step 2: Determine what phrases are

most important in the local context Step 3: Compute the probabilities of

humans removing a certain type of phrase

Step 4: Make the final decision

23

Step 1: Use linguistic knowledge to decide what MUST NOT be removed

Syntactic knowledge from a large-scale, reusable lexicon we have constructed convince: meaning 1: NP-PP :PVAL (“of”) (E.g., “He convinced me of his innocence”)

NP-TO-INF-OC (E.g., “He convinced me to go to the party”)

meaning 2: ... Required syntactic arguments are not

removed

24

Saudi Arabia on Tuesday decided to sign… The official Saudi Press Agency reported

that King Fahd made the decision during a cabinet meeting in Riyadh, the Saudi capital.

The meeting was called in response to … the Saudi foreign minister, that the Kingdom…

An account of the Cabinet discussions and decisions at the meeting…

The agency...

Step 2: Determining context importance based on lexical links

25





The agency...


26





The agency...


27

Step 3: Compute probabilities of humans removing a phrase

verb(will give)

vsubc(when)

subj(V-chip)

iobj(parents)

obj(device)

ndet(a)

adjp(and)

lconj(new)

rconj(revolutionary)

Prob(“when_clause is removed”| “v=give”)

Prob (“to_infinitive modifier is removed” | “n=device”)

28

Step 4: Make the final decision

verb(will give)

vsubc(when)

subj(V-chip)

iobj(parents)

ndet(a)

adjp(and)

lconj(new)

rconj(revolutionary)

L Cn Pr

L Cn Pr

L Cn Pr L Cn Pr L Cn Pr

L Cn Pr

L Cn Pr L Cn Pr

obj(device)

L Cn Pr

L -- linguisticCn -- contextPr -- probabilities

29

Evaluation of Reduction

Success rate: 81.3% 500 sentences reduced by humans Baseline: 43.2% (remove all the clauses,

prepositional phrases, to-infinitives,…) Reduction rate: 32.7%

Professionals: 41.8% Details in (Jing-ANLP00)

30

Multi-Document Summarization Research Focus Monitor variety of online information sources

News, multilingual Email

Gather information on events across source and time

Same day, multiple sources Across time

Summarize Highlighting similarities, new information, different

perspectives, user specified interests in real-time

31

Our Approach

Use a hybrid of statistical and linguistic knowledge

Statistical analysis of multiple documents Identify important new, contradictory information

Information fusion and rule-driven content selection

Generation of summary sentences By re-using phrases Automatic editing/rewriting summary

32

NewsblasterIntegrated in online environment for daily news updateshttp://newsblaster.cs.columbia.edu/

Ani Nenkova

David Elson

http://newsblaster.cs.columbia.edu/nlp/newsblaster

33

Newsblaster

http://newsblaster.cs.columbia.edu/ Clustering articles into events Categorization by broad topic Multi-document summarization Generation of summary sentences

Fusion Editing of references

http://newsblaster.cs.columbia.edu/

34

Newsblaster Architecture Crawl News Sites

Form Clusters

Categorize

TitleClusters

SummaryRouter

SelectImages

EventSummary

BiographySummary

Multi-Event

Convert Output to HTML

36

Fusion

37

Theme Computation

Input: A set of related documents Output: Sets of sentences that “mean”

the same thing Algorithm

Compute similarity across sentences using the Cosine Metric

Can compare word overlap or phrase overlap (PLACEHOLDER: IR vector space model)

38

Sentence Fusion Computation Common information identification

Alignment of constituents in parsed theme sentences: only some subtrees match

Bottom-up local multi-sequence alignment Similarity depends on

Word/paraphrase similarity Tree structure similarity

Fusion lattice computation Choose a basis sentence Add subtrees from fusion not present in basis Add alternative verbalizations Remove subtrees from basis not present in fusion

Lattice linearization Generate all possible sentences from the fusion lattice Score sentences using statistical language model

41

Tracking Across Days Users want to follow a story across time and watch it

unfold Network model for connecting clusters across days

Separately cluster events from today’s news Connect new clusters with yesterday’s news Allows for forking and merging of stories

Interface for viewing connections Summaries that update a user on what’s new

Statistical metrics to identify differences between article pairs Uses learned model of features Identifies differences at clause and paragraph levels

46

Different Perspectives

Hierarchical clustering Each event cluster is divided into clusters by

country

Different perspectives can be viewed side by side

Experimenting with update summarizer to identify key differences between sets of stories

50

Multilingual Summarization

Given a set of documents on the same event

Some documents are in English

Some documents are translated from other languages

51

Issues for Multilingual Summarization Problem: Translated text is errorful

Exploit information available during summarization

Similar documents in cluster

Replace translated sentences with similar English

Edit translated text Replace named entities with extractions from similar English

52

Multilingual RedundancyBAGDAD. - A total of 21 prisoners has been died and a hundred more hurt by firings from mortar in the jail of Abu Gharib (to 20 kilometers to the west of Bagdad), according to has informed general into the U.S.A. Marco Kimmitt.

Bagdad in the Iraqi capital Aufstaendi attacked Bagdad on Tuesday a prison with mortars and killed after USA gifts 22 prisoners. Further 92 passengers of the Abu Ghraib prison were hurt, communicated a spokeswoman of the American armed forces.

The Iraqi being stationed US military shot on the 20th, the same day to the allied forces detention facility which is in アブグレイブ of the Baghdad west approximately 20 kilometers, mortar 12 shot and you were packed, 22 Iraqi human prisoners died, it announced that nearly 100 people were injured.

BAGHDAD, Iraq – Insurgents fired 12 mortars into Baghdad's Abu Ghraib prison Tuesday, killing 22 detainees and injuring 92, U.S. military officials said.

Germ

anSpanish

JapaneseEnglish

53

Multilingual RedundancyBAGDAD. - A total of 21 prisoners has been died and a hundred more hurt by firings from mortar in the jail of Abu Gharib (to 20 kilometers to the west of Bagdad), according to has informed general into the U.S.A. Marco Kimmitt.

Bagdad in the Iraqi capital Aufstaendi attacked Bagdad on Tuesday a prison with mortars and killed after USA gifts 22 prisoners. Further 92 passengers of the Abu Ghraib prison were hurt, communicated a spokeswoman of the American armed forces.

The Iraqi being stationed US military shot on the 20th, the same day to the allied forces detention facility which is in アブグレイブ of the Baghdad west approximately 20 kilometers, mortar 12 shot and you were packed, 22 Iraqi human prisoners died, it announced that nearly 100 people were injured.

BAGHDAD, Iraq – Insurgents fired 12 mortars into Baghdad's Abu Ghraib prison Tuesday, killing 22 detainees and injuring 92, U.S. military officials said.

Germ

anSpanish

JapaneseEnglish

54

Multilingual Similarity-based Summarization

ستجوا ب

القالفDeutsch

erText

日本語テキスト

EnglishTextEnglishTextEnglishText

Related English Documents

Documents on the same Event

MachineTranslation

ArabicTextGermanText

JapaneseText

DetectSimilar

Sentences

Replace / rewrite MT sentences

EnglishSumma

ry

Select summary sentences

Simplify English

Sentences

55

Sentence 1Iraqi President Saddam Hussein that the government of Iraq

over 24 years in a "black" near the port of the northern Iraq after nearly eight months of pursuit was considered the largest in history .

Similarity 0.27: Ousted Iraqi President Saddam Hussein is in custody following his dramatic capture by US forces in Iraq.

Similarity 0.07: Saddam Hussein, the former president of Iraq, has been captured and is being held by US forces in the country.

Similarity 0.04: Coalition authorities have said that the former Iraqi president could be tried at a war crimes tribunal, with Iraqi judges presiding and international legal experts acting as advisers.

56

Sentence Simplification

Machine translated sentences long and ungrammatical

Use sentence simplification on English sentences to reduce to approximately “one fact” per sentence

Use Arabic sentences to find most similar simple sentences

Present multiple high similarity sentences

57

Simplification Examples 'Operation Red Dawn', which led to the capture of

Saddam Hussein, followed crucial information from a member of a family close to the former Iraqi leader. ' Operation Red Dawn' followed crucial information from a

member of a family close to the former Iraqi leader. Operation Red Dawn led to the capture of Saddam Hussein.

Saddam Hussein had been the object of intensive searches by US-led forces in Iraq but previous attempts to locate him had proved unsuccessful. Saddam Hussein had been the object of intensive searches

by US-led forces in Iraq. But previous attempts to locate him had proved unsuccessful.

58

Rewrite proper and common nouns to remove MT errors (Siddharthan and McKeown 05)

Use redundancy in input to summarization and multiple translations to build attribute value matrices (AVMs)

Record country, role, description for all people Record name variants

Use generation grammar with semantic categories (role, organization, location) to re-order phrases for fluent output

60

Evaluation

DUC (Document Understanding Conference): run by NIST yearly

Manual creation of topics (sets of documents) 2-7 human written summaries per topic How well does a system generated summary

cover the information in a human summary? Metrics

Rouge Pyramid

61

Rouge ROUGE version 1.2.1:

Publicly available at: http://www.isi.edu/~cyl/ROUGE Version 1.2.1 includes:

ROUGE-N - n-gram-based co-occurrence statistics ROUGE-L - longest common subsequence-based (LCS) co-occurrence statistics ROUGE-W - LCS-based co-occurrence statistics favoring consecutive LCSes

Measures recall Rouge-1: How many unigrams in the human

summary did the system summary find? Rouge-2: How many bigrams?

62

Pyramids Uses multiple human summaries

Previous data indicated 5 needed for score stability

Information is ranked by its importance Allows for multiple good summaries A pyramid is created from the human

summaries Elements of the pyramid are content units System summaries are scored by comparison

with the pyramid

63

Summarization Content Units

Near-paraphrases from different human summaries

Clause or less

Avoids explicit semantic representation

Emerges from analysis of human summaries

64

SCU: A cable car caught fire (Weight = 4)A. The cause of the fire was unknown.B. A cable car caught fire just after entering a

mountainside tunnel in an alpine resort in Kaprun, Austria on the morning of November 11, 2000.

C. A cable car pulling skiers and snowboarders to the Kitzsteinhorn resort, located 60 miles south of Salzburg in the Austrian Alps, caught fire inside a mountain tunnel, killing approximately 170 people.

D. On November 10, 2000, a cable car filled to capacity caught on fire, trapping 180 passengers inside the Kitzsteinhorn mountain, located in the town of Kaprun, 50 miles south of Salzburg in the central Austrian Alps.

65

SCU: The cause of the fire is unknown (Weight = 1)A. The cause of the fire was unknown.B. A cable car caught fire just after entering a




66

SCU: The accident happened in the Austrian Alps (Weight = 3)A. The cause of the fire was unknown.B. A cable car caught fire just after entering a




67

Idealized representation

Tiers of differentially weighted SCUs

Top: few SCUs, high weight

Bottom: many SCUs, low weight

W=1

W=2

W=3

68

Pyramid Score

SCORE = D/MAX

D: Sum of the weights of the SCUs in a summary

MAX: Sum of the weights of the SCUs in a ideally informative summary

Measures the proportion of good information in the summary: precision

69

User Study: Objectives

Does multi-document summarization help?

Do summaries help the user find information needed to perform a report writing task?

Do users use information from summaries in gathering their facts?

Do summaries increase user satisfaction with the online news system?

Do users create better quality reports with summaries? How do full multi-document summaries compare with

minimal 1-sentence summaries such as Google News?

70

User Study: Design

Four parallel news systems Source documents only; no summaries Minimal single sentence summaries (Google

News) Newsblaster summaries Human summaries

All groups write reports given four scenarios A task similar to analysts Can only use Newsblaster for research Time-restricted

71

User Study: Execution

4 scenarios 4 event clusters each 2 directly relevant, 2 peripherally relevant Average 10 documents/cluster

45 participants Balance between liberal arts, engineering 138 reports

Exit survey Multiple-choice and open-ended questions

Usage tracking Each click logged, on or off-site

72

“Geneva” Prompt

The conflict between Israel and the Palestinians has been difficult for government negotiators to settle. Most recently, implementation of the “road map for peace”, a diplomatic effort sponsored by ……

Who participated in the negotiations that produced the Geneva Accord?

Apart from direct participants, who supported the Geneva Accord preparations and how?

What has the response been to the Geneva Accord by the Palestinians?

73

Measuring Effectiveness

Score report content and compare across summary conditions

Compare user satisfaction per summary condition

Comparing where subjects took report content from

75

User Satisfaction

More effective than a web search with Newsblaster

Not true with documents only or single-sentence summaries

Easier to complete the task with summaries than with documents only

Enough time with summaries than documents only

Summaries helped most 5% single sentence summaries 24% Newsblaster summaries 43% human summaries

76

User Study: Conclusions

Summaries measurably improve a news browswer’s effectiveness for research

Users are more satisfied with Newsblaster summaries are better than single-sentence summaries like those of Google News

Users want search Not included in evaluation

77

Questions (from Sparck Jones) Should we take the reader into account and how? Need more power than text extraction and more

flexibility than fact extraction (p. 4) “Similarly, the notion of a basic summary, i.e., one

reflective of the source, makes hidden fact assumptions, for example that the subject knowledge of the output’s readers will be on a par with that of the readers for whom the source was intended. (p. 5)”

Is the state of the art sufficiently mature to allow summarization from intermediate representations and still allow robust processing of domain independent material?

Evaluation: gold standard vs. user study? Difficulty of evaluation?

Text Summarization: News and Beyond

Documents

Transcript of Text Summarization: News and Beyond